Since you haven't provided the dataset on which you are wokring it is difficult to say that you model has been overfitted or not. Generally overfitting takes place when we have limited data for training or when we train the model for more epochs than required, in order to reduce the training error over a small dataset or for more number of epochs the model tends to learn the details of the dataset and not the general trend. Try giving different number of epochs and check the graph for loss at each epoch, the point at which the loss stops decreasing is generally the point of epochs at which you should stop the training process.
100% Classification accuracy
1 次查看(过去 30 天)
显示 更早的评论
Hello all,
I am creating MLP with mushroom dataset from UCI in Matlab.It is a binary classification task with balaced class. In this i am getting 100% classification accuracy... am i overfitting? or going wrong somewhere?
Please see the code below and help me where i am going wrong.
thank you
0 个评论
采纳的回答
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Classification 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!